Customized image reprocessing system using a machine learning model

A system comprising:

• one or more processors;
• and
• a non-transitory computer readable storage medium comprising instructions that when executed by the one or processors cause the one or more processors to perform operations comprising:
• detecting a request to reprocess an image captured by a camera, the image associated with sensor data representing characteristics of an output of a digital image sensor of the camera, wherein the camera is a front facing camera of a client device;
• accessing flash calibration parameters associated with a user identification, the flash calibration parameters being previously saved characteristics of a front flash view that operates in lieu of a front flash of the camera, the front flash view overlaid over a camera view user interface (UI), the camera view UI comprising an output of the digital image sensor of the camera;
• reprocessing the image at a pixel level by executing a machine learning model, the machine learning model using the image, the sensor data and the flash calibration parameters as input, the reprocessing resulting in a reprocessed image;
• and
• causing display of the reprocessed image at the client device.

A machine-readable non-transitory storage medium having instruction data executable by a machine to cause the machine to perform operations comprising:

• detecting a request to reprocess an image captured by a camera, the image associated with sensor data representing characteristics of an output of a digital image sensor of the camera, wherein the camera is a front facing camera of a client device;
• accessing flash calibration parameters associated with a user identification, the flash calibration parameters being previously saved characteristics of a front flash view that operates in lieu of a front flash of the camera, the front flash view overlaid over a camera view user interface (UI), the camera view UI comprising an output of the digital image sensor of the camera;
• reprocessing the image at a pixel level by executing a machine learning model, the machine learning model using the image, the sensor data and the flash calibration parameters as input, the reprocessing resulting in a reprocessed image;
• and
• causing display of the reprocessed image at the client device.